Enrique Romero

Temperature effects on the hydraulic behaviour of an unsaturated clay

The influence of temperature on the hydraulic properties of unsaturated clays is of major concern in the design of engineered barriers in underground repositories for high-level radioactive waste disposal. This paper presents an experimental study centred on the investigation of the influence of temperature on soil hydraulic properties related to water retention and permeability. Laboratory tests were conducted on artificially prepared unsaturated fabrics obtained from a natural kaolinitic-illitic clay. Special attention is given to the testing procedures involving controlled suction and temperature oedometer cells and the application of the vapour equilibrium technique at high temperatures. Retention curves at different temperatures show that total suction tends to reduce with increasing temperatures at constant water content. Temperature influence on water permeability is more relevant at low matric suctions corresponding to bulk water preponderance (inter-aggregate zone). Below a degree of saturation of 75% no clear effect is detected. Experimental data show that temperature dependence on permeability at constant degree of saturation and constant void ratio is smaller than what could be expected from the thermal change in water viscosity. This behaviour suggests that phenomena such as porosity redistribution and thermo-chemical interactions, which alter clay fabric and pore fluid, can be relevant.

Performing Feature Selection With Multilayer Perceptrons

An experimental study on two decision issues for wrapper feature selection (FS) with multilayer perceptrons and the sequential backward selection (SBS) procedure is presented. The decision issues studied are the stopping criterion and the network retraining before computing the saliency. Experimental results indicate that the increase in the computational cost associated with retraining the network with every feature temporarily removed before computing the saliency is rewarded with a significant performance improvement. Despite being quite intuitive, this idea has been hardly used in practice. A somehow nonintuitive conclusion can be drawn by looking at the stopping criterion, suggesting that forcing overtraining may be as useful as early stopping. A significant improvement in the overall results with respect to learning with the whole set of variables is observed.

A Comparative Study of Soil Suction Measurement Using Two Different High-Range Psychrometers

An extensive experimental study was performed to compare the measurement capabilities within different ranges of two total suction measurement equipment: SMI transistor psychrometers and a chilled-mirror dew-point psychrometer (WP4 Dewpoint PotentiaMeter). The equipment were used in a systematic way to determine the relative humidity of the environment surrounding different compacted clayey soils along drying paths and covering a wide total suction range (0.1 to 70 MPa). The equipment description and the calibration protocols followed are presented, as well as suggestions regarding the improvement of their performance. The water retention curves of two different compacted clayey soils are presented and commented by taking into account the corrections proposed for the readings. A possible explanation for differences in the measurements observed between both instruments in the high suction range is presented in terms of the hydraulic paths undergone by the soils during the measurement period.

Classification of human brain tumours from MRS data using Discrete Wavelet Transform and Bayesian Neural Networks

The diagnosis of brain tumours is an extremely sensitive and complex clinical task that must rely upon information gathered through non-invasive techniques. One such technique is Magnetic Resonance Spectroscopy. In this task, radiology experts are likely to benefit from the support of computer-based systems built around robust classification processes. In this paper, a Discrete Wavelet Transform procedure was applied to the pre-processing of spectra corresponding to several brain tumour pathologies. This procedure does not alleviate the high dimensionality of the data by itself. For this reason, dimensionality reduction was subsequently implemented using Moving Window with Variance Analysis for feature selection or Principal Component Analysis for feature extraction. The combined method yielded very encouraging results in terms of diagnostic discriminatory binary classification using Bayesian Neural Networks. In most cases, the classification accuracy improved on previously reported results.

Volume change behaviour of a compacted scaly clay during cyclic suction changes

The research presented in this paper focuses on the investigation and modelling of the volume change response of compacted tectonised clay samples subjected to several wetting and drying cycles in controlled-suction oedometers. Oedometer tests were carried out under different values of constant vertical net stress, and wetting and drying cycles were performed varying applied matric suction between 10 and 800 kPa. The investigation was complemented with a study of the material microstructure to support the interpretation of the overall mechanical response. At a microscopic level, the material is characterized by different types of particle assemblages, scales, and clay aggregates. One of these assemblages was also subjected to a relative humidity cycle in an environmental scanning electron microscope (ESEM) to investigate the reversibility of the mechanical response. Based on the experimental results, the clay volume change behaviour is discussed and interpreted within the context of a double structure elastoplastic model. The procedure used to derive elastic and plastic constitutive parameters is presented. Comparison of test results with model predictions shows a satisfactory agreement between measured and calculated strain evolution.

Feature and model selection with discriminatory visualization for diagnostic classification of brain tumors

Machine Learning (ML) and related methods have of late made significant contributions to solving multidisciplinary problems in the field of oncology diagnosis. Human brain tumor diagnosis, in particular, often relies on the use of non-invasive techniques such as Magnetic Resonance Imaging (MRI) and Spectroscopy (MRS). In this paper, MRS data of human brain tumors are analyzed in detail. The high dimensionality of the MR spectra makes difficult both their classification and the interpretation of the obtained results, thus limiting their usability in practical medical settings. The use of dimensionality reduction techniques is therefore advisable. In this work, we apply feature selection methods and several off-the-shelf classifiers on various ^1H-MRS modalities: long and short echo times and an ad hoc combination of both. The introduction of bootstrap resampling techniques permits the obtention of mean performance estimates and their variability. Our experimental findings indicate that the feature selection process enhances the classification performance compared to using the full set of features. We also show that the use of combined information from the different echo times is a better strategy for small numbers of spectral frequencies; however, the use of ever greater numbers of short echo time frequencies permits the obtention of many models with similar performance. The final induced models offer very attractive solutions both in terms of prediction accuracy and number of involved spectral frequencies, which are also amenable to metabolic interpretation. A linear dimensionality-reduction technique that preserves class discrimination capabilities is used for visualizing the data corresponding to the selected frequencies.

Margin maximization with feed-forward neural networks: a comparative study with SVM and AdaBoost

Feed-forward Neural Networks (FNN) and Support Vector Machines (SVM) are two machine learning frameworks developed from very di:erent starting points of view. In this work a new learning model for FNN is proposed such that, in the linearly separable case, it tends to obtain the same solution as SVM. The key idea of the model is a weighting of the sum-of-squares error function, which is inspired by the AdaBoost algorithm. As in SVM, the hardness of the margin can be controlled, so that this model can be also used for the non-linearly separable case. In addition, it is not restricted to the use of kernel functions, and it allows to deal with multiclass and multilabel problems as FNN usually do. Finally, it is independent of the particular algorithm used to minimize the error function. Theoretic and experimental results on synthetic and real-world problems are shown to con=rm these claims. Several empirical comparisons among this new model, SVM, and AdaBoost have been made in order to study the agreement between the predictions made by the respective classi=ers. Additionally, the results obtained show that similar performance does not imply similar predictions, suggesting that di:erent models can be combined leading to better performance. c

A new incremental method for function approximation using feed-forward neural networks

A sequential method for approximating vectors in Hilbert spaces, called sequential approximation with optimal coefficients and interacting frequencies (SAOCIF), is presented. SAOCIF combines two key ideas. The first one is the optimization of the coefficients. The second one is the flexibility to choose the frequencies. The approximations defined by SAOCIF maintain orthogonal-like properties. The theoretical results obtained prove that, under reasonable conditions, the residue of the approximation obtained with SAOCIF (in the limit) is the best one that can be obtained with any subset of the given set of vectors. In the particular case of L/sup 2/, it can be applied to approximations by algebraic polynomials, Fourier series, wavelets and feed-forward neural networks, among others. Also, a particular algorithm with feed-forward neural networks is presented. The method combines the locality of sequential approximations, where only one frequency is found at every step, with the globality of non-sequential ones, where every frequency interacts with the others. Experimental results show a very satisfactory performance.

Outlier exploration and diagnostic classification of a multi-centre 1H-MRS brain tumour database

Non-invasive techniques such as magnetic resonance spectroscopy (MRS) are often required for assisting the diagnosis of tumours. Radiologists are not always accustomed to make sense of the biochemical information provided by MRS and they may benefit from computer-based support in their decision making. The high dimensionality of the MR spectra obscures atypical aspects of the data that may jeopardize their classification. In this study, we describe a method to overcome this problem that combines nonlinear dimensionality reduction, outlier detection, and expert opinion. MR spectra subsequently undergo a feature selection process followed by classification. The impact of outlier removal on classification performance is assessed.

Laboratory and Field Testing of Unsaturated Soils

The scope of this special issue focuses on recent advances in laboratory and field testing of unsaturated soils. Leading researchers from fourteen countries to represent global research in the area of experimental unsaturated soil mechanics have been invited to contribute to this issue. Twelve reports are presented dealing with measurement and control of suction and water content, mechanical, hydraulic, and geo-environmental testing, microstructure investigation, and applications of unsaturated soil monitoring to engineering behaviour of geo-structures.